pdf-parser.js 4.6.0 → 4.8.0

package/dist/read.cjs

@@ -497,13 +497,18 @@ function imagePlacementFrom(matrix) {
 		rotationDeg: rotationDeg !== 0 ? rotationDeg : void 0
 	};
 }
-function registerExtractedImage(format, bytes, widthPx, heightPx, images) {
+function registerExtractedImage(format, bytes, widthPx, heightPx, images, original) {
 	const imageId = `img${require_bytes_crc32.crc32(bytes).toString(16)}`;
 	if (!(imageId in images)) images[imageId] = {
 		format,
 		base64: require_util_base64.bytesToBase64(bytes),
 		widthPx,
-		heightPx
+		heightPx,
+		...original !== void 0 ? { original: {
+			filter: original.filter,
+			base64: require_util_base64.bytesToBase64(original.bytes),
+			...original.globalsBytes !== void 0 ? { jbig2GlobalsBase64: require_util_base64.bytesToBase64(original.globalsBytes) } : {}
+		} } : {}
 	};
 	return imageId;
 }
@@ -514,7 +519,7 @@ function resolveCachedImageId(dict, raw, images, cache, resolver, sink) {
 		cache.set(dict, null);
 		return;
 	}
-	const imageId = registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images);
+	const imageId = registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images, decoded.original);
 	cache.set(dict, imageId);
 	return imageId;
 }
@@ -536,7 +541,7 @@ function convertInlineImage(item, pageMatrix, images, resolver, sink) {
 	if (decoded === void 0) return;
 	return {
 		kind: "image",
-		imageId: registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images),
+		imageId: registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images, decoded.original),
 		...imagePlacementFrom(require_matrix.multiplyMatrices(item.matrix, pageMatrix)),
 		...item.layerName !== void 0 ? { layer: item.layerName } : {}
 	};

package/dist/read.js

@@ -496,13 +496,18 @@ function imagePlacementFrom(matrix) {
 		rotationDeg: rotationDeg !== 0 ? rotationDeg : void 0
 	};
 }
-function registerExtractedImage(format, bytes, widthPx, heightPx, images) {
+function registerExtractedImage(format, bytes, widthPx, heightPx, images, original) {
 	const imageId = `img${crc32(bytes).toString(16)}`;
 	if (!(imageId in images)) images[imageId] = {
 		format,
 		base64: bytesToBase64(bytes),
 		widthPx,
-		heightPx
+		heightPx,
+		...original !== void 0 ? { original: {
+			filter: original.filter,
+			base64: bytesToBase64(original.bytes),
+			...original.globalsBytes !== void 0 ? { jbig2GlobalsBase64: bytesToBase64(original.globalsBytes) } : {}
+		} } : {}
 	};
 	return imageId;
 }
@@ -513,7 +518,7 @@ function resolveCachedImageId(dict, raw, images, cache, resolver, sink) {
 		cache.set(dict, null);
 		return;
 	}
-	const imageId = registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images);
+	const imageId = registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images, decoded.original);
 	cache.set(dict, imageId);
 	return imageId;
 }
@@ -535,7 +540,7 @@ function convertInlineImage(item, pageMatrix, images, resolver, sink) {
 	if (decoded === void 0) return;
 	return {
 		kind: "image",
-		imageId: registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images),
+		imageId: registerExtractedImage(decoded.format, decoded.bytes, decoded.widthPx, decoded.heightPx, images, decoded.original),
 		...imagePlacementFrom(multiplyMatrices(item.matrix, pageMatrix)),
 		...item.layerName !== void 0 ? { layer: item.layerName } : {}
 	};

package/dist/write.cjs

@@ -206,7 +206,28 @@ function preparePngImage(bytes, compress) {
 		}
 	};
 }
+function preparePassthroughImage(asset, compress) {
+	if (asset.original === void 0) throw new Error("preparePassthroughImage: asset carries no original stream");
+	const png = preparePngImage(require_util_base64.base64ToBytes(asset.base64), compress);
+	const entries = /* @__PURE__ */ new Map([
+		["Type", require_objects.pdfName("XObject")],
+		["Subtype", require_objects.pdfName("Image")],
+		["Width", require_objects.pdfNum(asset.widthPx)],
+		["Height", require_objects.pdfNum(asset.heightPx)],
+		["Filter", require_objects.pdfName(asset.original.filter === "jbig2" ? "JBIG2Decode" : "JPXDecode")]
+	]);
+	if (asset.original.filter === "jbig2") {
+		entries.set("ColorSpace", require_objects.pdfName("DeviceGray"));
+		entries.set("BitsPerComponent", require_objects.pdfNum(1));
+	}
+	return {
+		dict: require_objects.pdfDict(entries),
+		raw: require_util_base64.base64ToBytes(asset.original.base64),
+		...png.alpha !== void 0 ? { alpha: png.alpha } : {}
+	};
+}
 function prepareImage(asset, compress) {
+	if (asset.original !== void 0) return preparePassthroughImage(asset, compress);
 	const bytes = require_util_base64.base64ToBytes(asset.base64);
 	return asset.format === "jpeg" ? prepareJpegImage(bytes) : preparePngImage(bytes, compress);
 }
@@ -361,9 +382,13 @@ function writePdf(doc, options = {}) {
 		const prepared = prepareImage(asset, compress);
 		const imageNum = nextObjNum++;
 		const smaskNum = prepared.alpha === void 0 ? void 0 : nextObjNum++;
+		const globalsBase64 = asset.original?.filter === "jbig2" ? asset.original.jbig2GlobalsBase64 : void 0;
+		const globalsNum = globalsBase64 !== void 0 ? nextObjNum++ : void 0;
 		imageAllocs.set(imageId, {
 			imageNum,
 			smaskNum,
+			globalsNum,
+			globalsBase64,
 			resourceName: `Im${index + 1}`,
 			prepared
 		});
@@ -708,6 +733,14 @@ function writePdf(doc, options = {}) {
 				value: require_objects.pdfStream(alloc.prepared.alpha.dict, alloc.prepared.alpha.raw)
 			});
 		}
+		if (alloc.globalsNum !== void 0 && alloc.globalsBase64 !== void 0) {
+			const globalsRaw = require_util_base64.base64ToBytes(alloc.globalsBase64);
+			alloc.prepared.dict.entries.set("DecodeParms", require_objects.pdfDict({ JBIG2Globals: require_objects.pdfRef(alloc.globalsNum, 0) }));
+			objects.push({
+				num: alloc.globalsNum,
+				value: require_objects.pdfStream(require_objects.pdfDict(compress ? /* @__PURE__ */ new Map([["Filter", require_objects.pdfName("FlateDecode")]]) : /* @__PURE__ */ new Map()), compress ? require_bytes_flate.deflate(globalsRaw) : globalsRaw)
+			});
+		}
 		objects.push({
 			num: alloc.imageNum,
 			value: require_objects.pdfStream(alloc.prepared.dict, alloc.prepared.raw)

package/dist/write.js

@@ -205,7 +205,28 @@ function preparePngImage(bytes, compress) {
 		}
 	};
 }
+function preparePassthroughImage(asset, compress) {
+	if (asset.original === void 0) throw new Error("preparePassthroughImage: asset carries no original stream");
+	const png = preparePngImage(base64ToBytes(asset.base64), compress);
+	const entries = /* @__PURE__ */ new Map([
+		["Type", pdfName("XObject")],
+		["Subtype", pdfName("Image")],
+		["Width", pdfNum(asset.widthPx)],
+		["Height", pdfNum(asset.heightPx)],
+		["Filter", pdfName(asset.original.filter === "jbig2" ? "JBIG2Decode" : "JPXDecode")]
+	]);
+	if (asset.original.filter === "jbig2") {
+		entries.set("ColorSpace", pdfName("DeviceGray"));
+		entries.set("BitsPerComponent", pdfNum(1));
+	}
+	return {
+		dict: pdfDict(entries),
+		raw: base64ToBytes(asset.original.base64),
+		...png.alpha !== void 0 ? { alpha: png.alpha } : {}
+	};
+}
 function prepareImage(asset, compress) {
+	if (asset.original !== void 0) return preparePassthroughImage(asset, compress);
 	const bytes = base64ToBytes(asset.base64);
 	return asset.format === "jpeg" ? prepareJpegImage(bytes) : preparePngImage(bytes, compress);
 }
@@ -360,9 +381,13 @@ function writePdf(doc, options = {}) {
 		const prepared = prepareImage(asset, compress);
 		const imageNum = nextObjNum++;
 		const smaskNum = prepared.alpha === void 0 ? void 0 : nextObjNum++;
+		const globalsBase64 = asset.original?.filter === "jbig2" ? asset.original.jbig2GlobalsBase64 : void 0;
+		const globalsNum = globalsBase64 !== void 0 ? nextObjNum++ : void 0;
 		imageAllocs.set(imageId, {
 			imageNum,
 			smaskNum,
+			globalsNum,
+			globalsBase64,
 			resourceName: `Im${index + 1}`,
 			prepared
 		});
@@ -707,6 +732,14 @@ function writePdf(doc, options = {}) {
 				value: pdfStream(alloc.prepared.alpha.dict, alloc.prepared.alpha.raw)
 			});
 		}
+		if (alloc.globalsNum !== void 0 && alloc.globalsBase64 !== void 0) {
+			const globalsRaw = base64ToBytes(alloc.globalsBase64);
+			alloc.prepared.dict.entries.set("DecodeParms", pdfDict({ JBIG2Globals: pdfRef(alloc.globalsNum, 0) }));
+			objects.push({
+				num: alloc.globalsNum,
+				value: pdfStream(pdfDict(compress ? /* @__PURE__ */ new Map([["Filter", pdfName("FlateDecode")]]) : /* @__PURE__ */ new Map()), compress ? deflate(globalsRaw) : globalsRaw)
+			});
+		}
 		objects.push({
 			num: alloc.imageNum,
 			value: pdfStream(alloc.prepared.dict, alloc.prepared.raw)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pdf-parser.js",
-  "version": "4.6.0",
+  "version": "4.8.0",
   "description": "Hand-written, dependency-minimal PDF codec: parses arbitrary real-world PDFs and generates new ones, built on its own codec-owned LayoutDocument item model and Zod 4 codecs.",
   "type": "module",
   "repository": {
@@ -72,8 +72,8 @@
   ],
   "license": "MIT",
   "dependencies": {
-    "byte-codec": "1.4.2",
-    "document-schema.js": "7.10.0",
+    "byte-codec": "1.5.0",
+    "document-schema.js": "7.11.0",
     "fflate": "0.8.3",
     "zod": "4.4.3"
   },